CN103678719A - Recommended system for providing feedback through environment sensing actively - Google Patents
Recommended system for providing feedback through environment sensing actively Download PDFInfo
- Publication number
- CN103678719A CN103678719A CN201310754962.1A CN201310754962A CN103678719A CN 103678719 A CN103678719 A CN 103678719A CN 201310754962 A CN201310754962 A CN 201310754962A CN 103678719 A CN103678719 A CN 103678719A
- Authority
- CN
- China
- Prior art keywords
- module
- information
- characteristic
- identification target
- required identification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Abstract
The invention discloses a recommended system for providing feedback through environment sensing actively. The system comprises a signal input module, a segmentation module, a cloud knowledge base, an identification module, an analysis module and a display module, wherein the signal input module is used for acquiring environment information within a current sensing area; the segmentation module is used for extracting a required identification target and a prospect area artwork in the environment information; the cloud knowledge base provides all characteristic information corresponding to the required identification target; the identification module is used for extracting all strong characteristic value information in the prospect area artwork, carrying out characteristic comparison on the strong characteristic value information and all characteristic information of the required identification target, and acquiring characteristic objects and correlation behaviors when the similarity is high; and the analysis module receives and collects all characteristic objects and the correlation behaviors so as to obtain a recommended list and output through the display module. The system actively recommends objects, videos or software to a user through the environment information, so that the time and the energy of the user are saved.
Description
Technical field
The present invention relates to a kind of commending system, relate in particular to a kind of commending system that environment sensing provides feedback opinion that initiatively sees through.
Background technology
Nowadays, Internet technology is in development rapidly, and various information is also constantly being enriched user's life.Yet how user filters out required information and how to promote its required information to user in magnanimity information becomes important now research topic.
Existing commending system is all generally the hobby that judges user according to user's active input or historical record, then recommends Item Information to user.The method effect is limited, cannot initiatively for current environment information, make immediately feedback, a feast for the eyes at commodity, the epoch of information overabundance, user need to spend the plenty of time and go to carry out the selection of article, has not only wasted the time, and be also a test on energy.
Summary of the invention
The object of this invention is to provide a kind of time saving and energy saving, initiatively see through the commending system that environment sensing provides feedback opinion.
For achieving the above object, the present invention is a kind of initiatively sees through the commending system that environment sensing provides feedback opinion, and this system comprises signal input module, cuts apart module, high in the clouds knowledge base, recognition module, analysis module and display module;
Described signal input module is for obtaining the environmental information in current induction region;
The described module of cutting apart is for required identification target and the former figure of foreground area of extraction environment information, and required identification target is sent to high in the clouds knowledge base, and the former figure of foreground area is sent to recognition module;
Described high in the clouds knowledge base provides all characteristic informations of its correspondence according to the required identification target receiving;
Described recognition module is used for extracting all strong characteristic value information of the former figure of foreground area, and all characteristic informations of strong characteristic value information and required identification target are done to aspect ratio pair, obtains characteristic body and corelation behaviour when the two similarity is greater than 80%;
After described analysis module receives and gathers all characteristic bodies and corelation behaviour, by association, calculate to release with historical record and recommend inventory and export by display module like recently.
Described signal input module is minisize pick-up head, infrared camera or degree of depth camera.
Described environmental information comprises people information, personage's behavioural information, Item Information or the spatial information in environment.
The content of described recommendation inventory is article, application software or video.
The invention provides a kind of recommend method that environment sensing provides feedback opinion that initiatively sees through, the method comprises the following steps:
1), by signal input module, obtain the environmental information in current induction region, and environmental information is sent to and cuts apart module;
2), cut apart module the environmental information receiving done to pre-service, be uploaded to high in the clouds knowledge base after extracting required identification target, meanwhile, from environmental information, extract the former figure of foreground area and be uploaded to recognition module;
3), high in the clouds base module provides all characteristic informations of its correspondence according to cutting apart required identification target that module sends;
4), recognition module is carried out conversion processing to the former figure of foreground area of cutting apart module and sending, obtain strong characteristic value information, then all characteristic informations of required identification target in strong characteristic value information and high in the clouds knowledge base are carried out to aspect ratio pair, when the two similarity is high, record characteristic body and corelation behaviour, and be sent to analysis module;
5), after analysis module gathers all characteristic bodies that receive and corelation behaviour, by connection, calculate to find out with historical record and recommend inventory like recently;
6), recommend inventory to show by display module, make the user can be with reference to recommending inventory make a choice.
The present invention is by the changeable environmental information of all types of camera active obtainings, all characteristic informations of the strong characteristic value information extracting in environmental information and required identification target are carried out to aspect ratio pair, according to all characteristic bodies that obtain after comparison and the relevance of behavior, further obtain recommendation inventory, to recommend article, video or software to user intuitively, save user's time and energy, practical.
Accompanying drawing explanation
Below in conjunction with accompanying drawing, the specific embodiment of the present invention is described in further detail:
Fig. 1 initiatively sees through the structured flowchart that environment sensing provides the commending system of feedback opinion for the present invention.
Embodiment
As shown in Figure 1, the present invention is a kind of initiatively sees through the commending system that environment sensing provides feedback opinion, and this system comprises signal input module 1, cuts apart module 2, high in the clouds knowledge base 3, recognition module 4, analysis module 5 and display module 6;
Described signal input module 1 is for obtaining the environmental information in current induction region;
The described module 2 of cutting apart is for required identification target and the former figure of foreground area of extraction environment information, and required identification target is sent to high in the clouds knowledge base 3, and the former figure of foreground area is sent to recognition module 4;
Described high in the clouds knowledge base 3 provides all characteristic informations of its correspondence according to the required identification target receiving;
Described recognition module 4 is for extracting all strong characteristic value information of the former figure of foreground area, and all characteristic informations of strong characteristic value information and required identification target are done to aspect ratio pair, obtains characteristic body and corelation behaviour when the two similarity is greater than 80%;
After described analysis module 5 receives and gathers all characteristic bodies and corelation behaviour, by association, calculate to release with historical record and recommend inventory and export by display module 6 like recently.
Described signal input module 1 is minisize pick-up head, infrared camera or degree of depth camera.
Described environmental information comprises people information, personage's behavioural information, Item Information or the spatial information in environment.
The content of described recommendation inventory is article, application software or video.
The present invention also provides a kind of recommend method that environment sensing provides feedback opinion that initiatively sees through, and the method comprises the following steps:
1), by signal input module 1, obtain the environmental information in current induction region, and environmental information is sent to and cuts apart module;
2), cut apart 2 pairs of environmental informations that receive of module and do pre-service, be uploaded to high in the clouds knowledge base 3 after extracting required identification target, meanwhile, from environmental information, extract the former figure of foreground area and be uploaded to recognition module 4;
3), high in the clouds base module 3 provides all characteristic informations of its correspondence according to cutting apart required identification target that module sends;
4), 4 pairs of recognition module are cut apart the former figure of foreground area that module 2 sends and are carried out conversion processing, obtain strong characteristic value information, then all characteristic informations of required identification target in strong characteristic value information and high in the clouds knowledge base 3 are carried out to aspect ratio pair, when the two similarity is high, record characteristic body and corelation behaviour, and be sent to analysis module 5;
5), after analysis module 5 gathers all characteristic bodies that receive and corelation behaviour, by connection, calculate to find out with historical record and recommend inventory like recently;
6), recommend inventory to show by display module 6, make the user can be with reference to recommending inventory make a choice.
Environmental information that can the current induction region of active obtaining by above step still can be recommended article, video or software to user under changeable environment, saves user's time and energy, practical.
Claims (5)
1. initiatively see through the commending system that environment sensing provides feedback opinion, it is characterized in that: this system comprises signal input module, cuts apart module, high in the clouds knowledge base, recognition module, analysis module and display module;
Described signal input module is for obtaining the environmental information in current induction region;
The described module of cutting apart is for required identification target and the former figure of foreground area of extraction environment information, and required identification target is sent to high in the clouds knowledge base, and the former figure of foreground area is sent to recognition module;
Described high in the clouds knowledge base provides all characteristic informations of its correspondence according to the required identification target receiving;
Described recognition module is used for extracting all strong characteristic value information of the former figure of foreground area, and all characteristic informations of strong characteristic value information and required identification target are done to aspect ratio pair, obtains characteristic body and corelation behaviour when the two similarity is greater than 80%;
After described analysis module receives and gathers all characteristic bodies and corelation behaviour, by association, calculate to release with historical record and recommend inventory and export by display module like recently.
2. a kind of commending system that environment sensing provides feedback opinion that initiatively sees through according to claim 1, is characterized in that: described signal input module is minisize pick-up head, infrared camera or degree of depth camera.
3. a kind of commending system that environment sensing provides feedback opinion that initiatively sees through according to claim 1, is characterized in that: described environmental information comprises people information, personage's behavioural information, Item Information or the spatial information in environment.
4. a kind of commending system that environment sensing provides feedback opinion that initiatively sees through according to claim 1, is characterized in that: the content of described recommendation inventory is article, application software or video.
5. a kind of as described in one of claim 1-4 initiatively sees through the recommend method that environment sensing provides feedback opinion, it is characterized in that: said method comprising the steps of:
1), by signal input module, obtain the environmental information in current induction region, and environmental information is sent to and cuts apart module;
2), cut apart module the environmental information receiving done to pre-service, be uploaded to high in the clouds knowledge base after extracting required identification target, meanwhile, from environmental information, extract the former figure of foreground area and be uploaded to recognition module;
3), high in the clouds base module provides all characteristic informations of its correspondence according to cutting apart required identification target that module sends;
4), recognition module is carried out conversion processing to the former figure of foreground area of cutting apart module and sending, obtain strong characteristic value information, then all characteristic informations of required identification target in strong characteristic value information and high in the clouds knowledge base are carried out to aspect ratio pair, when the two similarity is high, record characteristic body and corelation behaviour, and be sent to analysis module;
5), after analysis module gathers all characteristic bodies that receive and corelation behaviour, by connection, calculate to find out with historical record and recommend inventory like recently;
6), recommend inventory to show by display module, make the user can be with reference to recommending inventory make a choice.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310754962.1A CN103678719B (en) | 2013-12-31 | 2013-12-31 | It is a kind of actively to pass through the commending system that environment sensing provides feedback opinion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310754962.1A CN103678719B (en) | 2013-12-31 | 2013-12-31 | It is a kind of actively to pass through the commending system that environment sensing provides feedback opinion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103678719A true CN103678719A (en) | 2014-03-26 |
| CN103678719B CN103678719B (en) | 2017-05-31 |
Family
ID=50316263
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310754962.1A Expired - Fee Related CN103678719B (en) | 2013-12-31 | 2013-12-31 | It is a kind of actively to pass through the commending system that environment sensing provides feedback opinion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103678719B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104268154A (en) * | 2014-09-02 | 2015-01-07 | 百度在线网络技术（北京）有限公司 | Recommended information providing method and device |
| CN109086789A (en) * | 2018-06-08 | 2018-12-25 | 四川斐讯信息技术有限公司 | A kind of image-recognizing method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100128927A1 (en) * | 2008-03-14 | 2010-05-27 | Sony Computer Entertainment Inc. | Image processing apparatus and image processing method |
| CN102254268A (en) * | 2011-05-19 | 2011-11-23 | 冠捷显示科技（厦门）有限公司 | Interactive network online shopping system and method |
| CN102982472A (en) * | 2012-11-29 | 2013-03-20 | 何松 | Method and device for automatically recommending similar commodities by terminal |
| CN103024471A (en) * | 2012-12-07 | 2013-04-03 | 康佳集团股份有限公司 | Rapid recommendation method for intelligent cloud television |
-
2013
- 2013-12-31 CN CN201310754962.1A patent/CN103678719B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100128927A1 (en) * | 2008-03-14 | 2010-05-27 | Sony Computer Entertainment Inc. | Image processing apparatus and image processing method |
| CN102254268A (en) * | 2011-05-19 | 2011-11-23 | 冠捷显示科技（厦门）有限公司 | Interactive network online shopping system and method |
| CN102982472A (en) * | 2012-11-29 | 2013-03-20 | 何松 | Method and device for automatically recommending similar commodities by terminal |
| CN103024471A (en) * | 2012-12-07 | 2013-04-03 | 康佳集团股份有限公司 | Rapid recommendation method for intelligent cloud television |
Non-Patent Citations (3)
| Title |
|---|
| ZHANG WEIGUO ET AL.: ""Target recognition algorithm based on block and SIFT features"", 《2013 IEEE INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING, COMMUNICATION AND COMPUTING》 * |
| 方辉等: ""基于WEB的制造信息主动推荐服务研究"", 《计算机集成制造系统》 * |
| 梁鹏 等: ""一种新的无监督前景目标检测方法"", 《计算机研究与发展》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104268154A (en) * | 2014-09-02 | 2015-01-07 | 百度在线网络技术（北京）有限公司 | Recommended information providing method and device |
| CN109086789A (en) * | 2018-06-08 | 2018-12-25 | 四川斐讯信息技术有限公司 | A kind of image-recognizing method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103678719B (en) | 2017-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10372988B2 (en) | Systems and methods for automatically varying privacy settings of wearable camera systems | |
| CN107404656B (en) | Live video recommended method, device and server | |
| CN104582187B (en) | Based on the record of recognition of face and Expression Recognition and lamp light control system and method | |
| JP6950912B2 (en) | Video search information provision method, equipment and computer program | |
| CN104410911B (en) | Based on the method for video feeling mark aid identification facial expression | |
| US20190327357A1 (en) | Information presentation method and device | |
| US11270368B2 (en) | Method and apparatus for presenting object based on biometric feature | |
| CN108959323B (en) | Video classification method and device | |
| CN108133057A (en) | For the editing in portable terminal and the device and method of shared content | |
| CN113810742A (en) | Virtual gift processing method and device, electronic equipment and storage medium | |
| US10600060B1 (en) | Predictive analytics from visual data | |
| CN103678719A (en) | Recommended system for providing feedback through environment sensing actively | |
| CN103578020A (en) | Commodity information pushing system and method | |
| Yu et al. | Vision-based hand recognition based on tof depth camera | |
| CN104102328A (en) | Information processing method and information processing equipment | |
| Hossain et al. | Automatic facial skin detection using Gaussian mixture model under varying illumination | |
| CN103279519A (en) | Article searching method and device | |
| CN109960442B (en) | Prompt information transmission method and device, storage medium and electronic device | |
| CN103927399A (en) | Information push method and device | |
| CN115687745A (en) | Multimedia data recommendation method and device, storage medium and computer equipment | |
| CN114846812A (en) | Abstract video generation method and device and server | |
| CN116132752B (en) | Video comparison group construction, model training and video scoring methods, devices and equipment | |
| CN110173866B (en) | Intelligent air supply method and device of air conditioner and air conditioner | |
| CN103839067A (en) | Method, device and system for obtaining article information | |
| Wang | 2D bar code recognition marking in metal parts |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170531 Termination date: 20181231 |